ARMFlow：用于在线三维人体反应生成的自回归平均流模型
ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation
把 MeanFlow 的单步速度预测与因果上下文编码器结合，用于在线人体反应动作生成；BSCE（用生成历史而非真值编码）是缓解自回归误差累积的可复用训练技巧，可迁移到其他流式动作/视频生成任务。
原文依据 We introduce Bootstrap Contextual Encoding (BSCE) in training, encoding generated history instead of the ground-truth ones
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维人体反应生成面临三大挑战：（1）高动作保真度，（2）实时推理，（3）面向在线场景的自回归适应性。现有方法无法同时满足这三点。我们提出 ARMFlow，一个基于平均流（MeanFlow）的自回归框架，对表演者与反应者动作之间的时序依赖进行建模。它由因果上下文编码器和基于 MLP 的速度预测器组成。我们在训练中引入自举上下文编码（BSCE），对生成的历史而非真值历史进行编码，以缓解自回归生成中的误差累积。我们进一步提出离线变体 ReMFlow，在离线方法中取得最优性能并具备最快的推理速度。我们的 ARMFlow 通过以下方式解决在线设置的关键局限：（1）借助全局上下文编码器增强语义对齐；（2）在单步推理中实现高精度与低延迟；（3）通过 BSCE 减少累积误差。我们的单步在线生成在 InterHuman 和 InterX 上以 FID 指标超越现有在线方法约 30%，同时在仅使用部分序列条件的情况下达到与离线最优方法相当的性能。代码见补充材料。
英文原文摘要 1259 字符
3D human reaction generation faces three main challenges: (1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously. We propose ARMFlow, a MeanFlow-based autoregressive framework that models temporal dependencies between actor and reactor motions. It consists of a causal context encoder and an MLP-based velocity predictor. We introduce Bootstrap Contextual Encoding (BSCE) in training, encoding generated history instead of the ground-truth ones, to alleviate error accumulation in autoregressive generation. We further introduce the offline variant ReMFlow , achieving state-of-the-art performance with the fastest inference among offline methods. Our ARMFlow addresses key limitations of online settings by: (1) enhancing semantic alignment via a global contextual encoder; (2) achieving high accuracy and low latency in a single-step inference; and (3) reducing accumulated errors through BSCE. Our single-step online generation surpasses existing online methods on InterHuman and InterX by about 30% in FID, while matching offline state-of-the-art performance despite using only partial sequence conditions. Code is available in the supplementary.